Abstract
Recently, pre-trained transformer-based models have achieved great success in the task of definition generation (DG). However, previous encoder-decoder models lack effective representation learning to contain full semantic components of the given word, which leads to generating under-specific definitions. To address this problem, we propose a novel contrastive learning method, encouraging the model to capture more detailed semantic representations from the definition sequence encoding. According to both automatic and manual evaluation, the experimental results on three mainstream benchmarks demonstrate that the proposed method could generate more specific and high-quality definitions compared with several state-of-the-art models.- Anthology ID:
- 2022.aacl-main.73
- Volume:
- Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
- Month:
- November
- Year:
- 2022
- Address:
- Online only
- Venues:
- AACL | IJCNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1001–1012
- Language:
- URL:
- https://aclanthology.org/2022.aacl-main.73
- DOI:
- Cite (ACL):
- Hengyuan Zhang, Dawei Li, Shiping Yang, and Yanran Li. 2022. Fine-grained Contrastive Learning for Definition Generation. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 1001–1012, Online only. Association for Computational Linguistics.
- Cite (Informal):
- Fine-grained Contrastive Learning for Definition Generation (Zhang et al., AACL-IJCNLP 2022)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/2022.aacl-main.73.pdf